Controlled sampling using ranked set sampling

Abstract

Based on ranked set sampling procedure, a technique to obtain a controlled preferable sample is introduced. Using this technique it is possible to obtain an approximate preferable sample from a population of interest. In particular, the technique can be used to obtain sample points that tend to be from a specific portion of a distribution such as the lower or upper quartiles. The performance of the technique is investigated under perfect and imperfect ranking. Some other related topics are also discussed.